Adi Haviv

Tel Aviv University
Not Every Image is Worth a Thousand Words: Quantifying Originality in Stable Diffusion
Adi Haviv

Bio

Adi Haviv is a Ph.D. candidate at Tel Aviv University, working under the guidance of Prof. Amit Bermano and Dr. Roi Livni. She has completed both his BSc and MSc at Tel Aviv University and has gained diverse industry experience, including a role as an applied research and engineering manager at eBay NYC. Her research primarily focuses on the interpretability and robustness of large deep neural models in natural language processing (NLP) and computer vision.

Abstract

This talk addresses the challenge of quantifying originality in text-to-image (T2I) generative diffusion models, with a focus on copyright originality. We propose a method that leverages textual inversion to measure the originality of an image based on the number of tokens required for its reconstruction by the model. Our approach is inspired by legal definitions of originality and aims to assess whether a model can produce original content without relying on specific prompts or having the training data of the model. We demonstrate our method using both a pre-trained stable diffusion model and a synthetic dataset, showing a correlation between the number of tokens and image originality. Further, we delve into the ability of models to generate unseen content and assess their generalization capabilities. Our findings suggest that T2I models are capable of generating original content and highlight the importance of training models on diverse datasets. This work contributes to the understanding of originality in generative models and has implications for copyright infringement cases.

Agenda

8:45 Reception
9:30 Opening remarks by WiDS TLV ambassadors Noah Eyal Altman, Or Basson, and Nitzan Gado
9:45 Dr. Aya Soffer, IBM: "Putting Generative AI to Work: What Have We Learned So Far?"
10:15 Prof. Reut Tsarfaty, Bar-llan University: "Will Hebrew Speakers Be Able to Use Generative AI in Their Native Tongue?"
10:45 Poster Pitches
10:55 Break
11:10 Lightning talks
12:30 Lunch & poster session
13:30 Roundtable session & poster session
14:15 Roundtable closing
14:30 Break
14:40 Naomi Ken Korem, Lightricks: "Mastering the Art of Generative Models: Training and Controlling Text-to-Video Models"
15:00 Dr. Yael Mathov, Intuit: "Surviving the AI-pocalypse: Your Guide to LLM Security"
15:20 Closing remarks
15:30 The end